llvm-project/llvm/test/Transforms/LoopVectorize/X86/pr42674.ll

42 lines
2.0 KiB
LLVM
Raw Normal View History

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt %s -loop-vectorize -instcombine -simplifycfg -mtriple=x86_64-unknown-linux-gnu -mcpu=skylake-avx512 -S | FileCheck %s
@bytes = global [128 x i8] zeroinitializer, align 16
; FIXME: We should end up with vector code for this loop, but don't because
; we try to create VF=64,UF=4 loop, but the scalar trip count is only 128 so
; the vector loop becomes dead code leaving only a scalar remainder.
define zeroext i8 @sum() {
; CHECK-LABEL: @sum(
; CHECK-NEXT: entry:
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT: [[R_010:%.*]] = phi i8 [ 0, [[ENTRY]] ], [ [[ADD:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [128 x i8], [128 x i8]* @bytes, i64 0, i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP0:%.*]] = load i8, i8* [[ARRAYIDX]], align 1
; CHECK-NEXT: [[ADD]] = add i8 [[TMP0]], [[R_010]]
; CHECK-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], 128
; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_END:%.*]], label [[FOR_BODY]], !llvm.loop !0
; CHECK: for.end:
; CHECK-NEXT: ret i8 [[ADD]]
;
entry:
br label %for.body
for.body: ; preds = %for.body, %entry
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
%r.010 = phi i8 [ 0, %entry ], [ %add, %for.body ]
%arrayidx = getelementptr inbounds [128 x i8], [128 x i8]* @bytes, i64 0, i64 %indvars.iv
%0 = load i8, i8* %arrayidx, align 1
%add = add i8 %0, %r.010
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond = icmp eq i64 %indvars.iv.next, 128
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body
%add.lcssa = phi i8 [ %add, %for.body ]
ret i8 %add.lcssa
}